def test_guess_encoding_ascii(self):
"""
Assert when ascii-only data is provided ascii is the guessed encoding.
"""
data = u'Twas bryllyg, and the slythy toves did gyre and gymble'
result = encoding_utils.guess_encoding(data.encode('ascii'))
self.assertEqual(result, 'ascii')
def test_guess_encoding_ascii(self):
"""
Assert when ascii-only data is provided ascii is the guessed encoding.
"""
data = u'Twas bryllyg, and the slythy toves did gyre and gymble'
result = encoding_utils.guess_encoding(data.encode('ascii'))
self.assertEqual(result, 'ascii')
def test_guess_encoding_favor_utf_8(self):
"""
Test that strings that could be UTF-8 or ISO-8859-2 result in UTF-8.
"""
data = u'Šabata'.encode('utf-8')
result = encoding_utils.guess_encoding(data)
chardet_result = chardet.detect(data)
self.assertEqual(result, 'utf-8')
self.assertEqual(chardet_result['encoding'], 'ISO-8859-2')
def test_guess_encoding_favor_utf_8(self):
"""
Test that strings that could be UTF-8 or ISO-8859-2 result in UTF-8.
"""
data = u'Šabata'.encode('utf-8')
result = encoding_utils.guess_encoding(data)
chardet_result = chardet.detect(data)
self.assertEqual(result, 'utf-8')
self.assertEqual(chardet_result['encoding'], 'ISO-8859-2')
def test_guess_encoding_favor_utf_8(self):
"""
Test that strings that could be UTF-8 or ISO-8859-* result in UTF-8.
python-chardet-3.0.4-2.fc27.noarch detects it as ISO-8859-9
python-chardet-2.2.1-1.el7_1.noarch detects it as ISO-8859-2
"""
data = 'Šabata'.encode('utf-8')
result = encoding_utils.guess_encoding(data)
chardet_result = chardet.detect(data)
self.assertEqual(result, 'utf-8')
if chardet.__version__[0] == '3':
self.assertEqual(chardet_result['encoding'], 'ISO-8859-9')
else:
self.assertEqual(chardet_result['encoding'], 'ISO-8859-2')
def test_guess_encoding_favor_utf_8(self):
"""
Test that strings that could be UTF-8 or ISO-8859-* result in UTF-8.
python-chardet-3.0.4-2.fc27.noarch detects it as ISO-8859-9
python-chardet-2.2.1-1.el7_1.noarch detects it as ISO-8859-2
"""
data = "Šabata".encode("utf-8")
result = encoding_utils.guess_encoding(data)
chardet_result = chardet.detect(data)
self.assertEqual(result, "utf-8")
if chardet.__version__[0] == "3":
self.assertEqual(chardet_result["encoding"], "ISO-8859-9")
else:
self.assertEqual(chardet_result["encoding"], "ISO-8859-2")
def test_guess_encoding_favor_utf_8(self):
"""
Test that strings that could be UTF-8 or ISO-8859-* result in UTF-8.
python-chardet-3.0.4-2.fc27.noarch detects it as ISO-8859-9
python-chardet-2.2.1-1.el7_1.noarch detects it as ISO-8859-2
"""
data = "Šabata".encode("utf-8")
result = encoding_utils.guess_encoding(data)
chardet_result = chardet.detect(data)
self.assertEqual(result, "utf-8")
if chardet.__version__[0] == "3":
self.assertEqual(chardet_result["encoding"], "ISO-8859-9")
else:
self.assertEqual(chardet_result["encoding"], "ISO-8859-2")
def test_guess_encoding_no_data(self):
result = encoding_utils.guess_encoding(u''.encode('utf-8'))
self.assertEqual(result, 'ascii')
def test_guess_encoding_no_data(self):
""" Test encoding_utils.guess_encoding() with an empty string """
result = encoding_utils.guess_encoding(''.encode('utf-8'))
self.assertEqual(result, 'ascii')
def test_guess_encoding_no_data(self):
""" Test encoding_utils.guess_encoding() with an empty string """
result = encoding_utils.guess_encoding(u''.encode('utf-8'))
self.assertEqual(result, 'ascii')
def test_guess_encoding_no_data(self):
""" Test encoding_utils.guess_encoding() with an empty string """
result = encoding_utils.guess_encoding("".encode("utf-8"))
self.assertEqual(result, "ascii")
def test_guess_encoding_no_data(self):
""" Test encoding_utils.guess_encoding() with an empty string """
result = encoding_utils.guess_encoding("".encode("utf-8"))
self.assertEqual(result, "ascii")